Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference

Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhang Zhang, Yuan Wan, Jiahui Hao, Zaili Yang, Huanhuan Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/8/1340
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144315498561536
author Yuhang Zhang
Yuan Wan
Jiahui Hao
Zaili Yang
Huanhuan Li
author_facet Yuhang Zhang
Yuan Wan
Jiahui Hao
Zaili Yang
Huanhuan Li
author_sort Yuhang Zhang
collection DOAJ
description Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions to improve the representation of feature interactions while mitigating the influence of confounding factors through causal inference. A novel high-order feature learning framework with causal inference is developed to enhance FGVC. A causal graph tailored to FGVC is constructed, and the causal assumptions of baseline models are analyzed to identify confounding factors. A reconstructed causal structure establishes meaningful interactions between individual images and image pairs. Causal interventions are applied by severing specific causal links, effectively reducing confounding effects and enhancing model robustness. The framework combines high-order feature fusion with interventional fine-grained learning by performing causal interventions on both classifiers and categories. The experimental results demonstrate that the proposed method achieves accuracies of 90.7% on CUB-200, 92.0% on FGVC-Aircraft, and 94.8% on Stanford Cars, highlighting its effectiveness and robustness across these widely used fine-grained recognition datasets. Comprehensive evaluations of these three widely used fine-grained recognition datasets demonstrate the proposed framework’s effectiveness and robustness.
format Article
id doaj-art-b504ffbd616a493fa8f8babcf88b932d
institution OA Journals
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-b504ffbd616a493fa8f8babcf88b932d2025-08-20T02:28:24ZengMDPI AGMathematics2227-73902025-04-01138134010.3390/math13081340Learning High-Order Features for Fine-Grained Visual Categorization with Causal InferenceYuhang Zhang0Yuan Wan1Jiahui Hao2Zaili Yang3Huanhuan Li4School of Mathematics and Statistics, Wuhan University of Technology, 122 Luoshi Road, Wuhan 430070, ChinaSchool of Mathematics and Statistics, Wuhan University of Technology, 122 Luoshi Road, Wuhan 430070, ChinaSchool of Mathematics and Statistics, Wuhan University of Technology, 122 Luoshi Road, Wuhan 430070, ChinaLiverpool Logistics, Offshore and Marine Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UKLiverpool Logistics, Offshore and Marine Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UKRecently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions to improve the representation of feature interactions while mitigating the influence of confounding factors through causal inference. A novel high-order feature learning framework with causal inference is developed to enhance FGVC. A causal graph tailored to FGVC is constructed, and the causal assumptions of baseline models are analyzed to identify confounding factors. A reconstructed causal structure establishes meaningful interactions between individual images and image pairs. Causal interventions are applied by severing specific causal links, effectively reducing confounding effects and enhancing model robustness. The framework combines high-order feature fusion with interventional fine-grained learning by performing causal interventions on both classifiers and categories. The experimental results demonstrate that the proposed method achieves accuracies of 90.7% on CUB-200, 92.0% on FGVC-Aircraft, and 94.8% on Stanford Cars, highlighting its effectiveness and robustness across these widely used fine-grained recognition datasets. Comprehensive evaluations of these three widely used fine-grained recognition datasets demonstrate the proposed framework’s effectiveness and robustness.https://www.mdpi.com/2227-7390/13/8/1340causal modelscausal inferencefine-grained visual categorizationfeature fusioncausal intervention
spellingShingle Yuhang Zhang
Yuan Wan
Jiahui Hao
Zaili Yang
Huanhuan Li
Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
Mathematics
causal models
causal inference
fine-grained visual categorization
feature fusion
causal intervention
title Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
title_full Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
title_fullStr Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
title_full_unstemmed Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
title_short Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
title_sort learning high order features for fine grained visual categorization with causal inference
topic causal models
causal inference
fine-grained visual categorization
feature fusion
causal intervention
url https://www.mdpi.com/2227-7390/13/8/1340
work_keys_str_mv AT yuhangzhang learninghighorderfeaturesforfinegrainedvisualcategorizationwithcausalinference
AT yuanwan learninghighorderfeaturesforfinegrainedvisualcategorizationwithcausalinference
AT jiahuihao learninghighorderfeaturesforfinegrainedvisualcategorizationwithcausalinference
AT zailiyang learninghighorderfeaturesforfinegrainedvisualcategorizationwithcausalinference
AT huanhuanli learninghighorderfeaturesforfinegrainedvisualcategorizationwithcausalinference